AI & Machine Learning MCP Servers

AI services, embeddings, LLM integration

2,891 servers

open-transcribe-mcp

40
uvx

Provider-independent speech-to-text over MCP.

1

Image Gen

40
npx Auth Required

Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.

1

grounder-mcp

40
uvx

Live web search, page fetch, and a token-capped cited evidence pack as MCP tools for local and cloud LLMs.

AI Guardian

40
uvx

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

iflow-mcp_excelsier-things3-enhanced-mcp

40
uvx Caution 72

Enhanced FastMCP server for Things 3 app integration with Claude Desktop and Windsurf - featuring reliability improvements, caching, and AppleScript bridge

@epicdm/flowstate-mcp-web-transport

40
npx

HTTP/SSE web transport for Model Context Protocol

4/wk

gpt-image-2-polza-mcp-server

40
uvx

GPT Image 2 generation and editing through the Polza API

Zerouter

40
Auth Required

AI API gateway MCP: Claude, GPT, Gemini, Grok & Kimi with one Zerouter API key, plus API pricing.

mem0-mcp-server

40
uvx

Model Context Protocol server that exposes the Mem0 long-term memory API as tools

atproto-mcp

40
uvx

MCP server providing AT Protocol documentation, lexicons, Bluesky API docs, and cookbook examples as a searchable knowledge base powered by semantic search.

@darient/code-analyzer-mcp

40
npx Caution 75

The Code Analyzer MCP Server is a Model Context Protocol (MCP) server that analyzes code vulnerabilities in directories using OpenAI models, enhancing software security for developers and AI.

6/wk

@passelin/mcp-server-speak

40
npx

A MCP server that provides the ability to speak text using the system's text-to-speech engine.

8/wk

cloudprice-mcp

40
uvx

FinOps MCP server: cloud + LLM pricing for AI assistants. AWS, Azure, GCP and OCI list prices, RI / Savings Plan break-even, TCO, migration, egress, spot, GPU, carbon, FOCUS 1.3 export, and token prices for ~3,600 LLM model/provider rows with a weekly price-change archive. No cloud account needed.

offline-mcp

40
uvx Caution 72

Local AI inference for Africa — Ollama, open weights, degraded-mode fallbacks. 6 tools.

gosce-authenticated-mcp-agent-aed9d5

40
uvx

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

cli-bridge-mcp

40
uvx

Expose the other AI CLIs installed on your machine (Gemini, Codex, Claude Code, Mistral, opencode, Ollama…) as MCP tools. Spawns the official CLI; no API keys.

@blocksifr/modelmeter

40
npx

AI Compute Savings CLI: detect and cut avoidable AI spend before the model runs. Traces commands, proxies MCP, and posts PR waste reports — metadata only, hash-chained receipts.

5/wk

com.brainiall/tts

40
Remote

Hosted pay-per-use TTS: 54 neural voices, 9 languages incl. Brazilian Portuguese. $10 free credits.

mcp-api-connect

40
npx

A tool for making HTTP requests through the Model Context Protocol (MCP)

6/wk

shieldpi-mcp

40
uvx Caution 72

MCP server for ShieldPi Watchtower — run LLM security scans, generate drop-in guardrails from scan findings, operate the AI SOC analyst (incident triage + kill-chain reconstruction), and query the live agent monitor from Claude Desktop / Cursor / Continue.

coinrailz-mcp

40
uvx

MCP server exposing 63 Coin Railz tools — crypto analytics, trading signals, NASA/ESA satellite data, IoT sensors, AI inference, and prediction markets

gosce-authenticated-llm-mcp-agent

40
uvx

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

codex-mcp-server

40
uvx

MCP server for Codex CLI with tmux persistence, git worktree isolation, and async dispatch.

gosce-structured-output-mcp-agent-langchain-core

40
uvx

Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).

← Prev Page 71 of 121 Next →